Truncated max-of-convex models
Truncated convex models (TCM) are a special case of pairwise random fields that have been widely used in computer vision. However, by restricting the order of the potentials to be at most two, they fail to capture useful image statistics. We propose a natural generalization of TCM to high-order rand...
Hlavní autoři: | Pansari, P, Mudigonda, P |
---|---|
Médium: | Conference item |
Vydáno: |
Computer Vision Foundation
2017
|
Podobné jednotky
-
Truncated max-of-convex models
Autor: Mudigonda, P, a další
Vydáno: (2017) -
Improved moves for truncated convex models
Autor: Kumar, MP, a další
Vydáno: (2009) -
Improved moves for truncated convex models
Autor: Pawan Kumar, M, a další
Vydáno: (2011) -
Optimal submodular extensions for marginal estimation
Autor: Pansari, P, a další
Vydáno: (2018) -
On hyperspaces of max-plus and max-min convex sets
Autor: Bazylevych Lidiya, a další
Vydáno: (2017-01-01)